Skip to content
POST/api/v1/security/auto-guardrails

Auto-generate guardrails from red-team findings

Takes an array of red-team findings and synthesizes guardrail rules that would have caught the successful attacks. Returns generated guardrails, coverage, and recommendations inline.

Authentication

Send Authorization: Bearer YOUR_API_KEY on every request. Generate API keys at /dashboard/settings/api-keys.

Request body required

Example

{
  "findings": [
    {
      "severity": "string",
      "input": "string",
      "type": "string",
      "category": "string",
      "attackCategory": "string",
      "title": "string",
      "description": "string",
      "output": "string"
    }
  ]
}
Schema
{
  "application/json": {
    "schema": {
      "type": "object",
      "properties": {
        "findings": {
          "minItems": 1,
          "maxItems": 200,
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "severity": {
                "type": "string",
                "maxLength": 60
              },
              "input": {
                "type": "string",
                "minLength": 1,
                "maxLength": 100000
              },
              "type": {
                "type": "string",
                "maxLength": 120
              },
              "category": {
                "type": "string",
                "maxLength": 120
              },
              "attackCategory": {
                "type": "string",
                "maxLength": 120
              },
              "title": {
                "type": "string",
                "maxLength": 500
              },
              "description": {
                "type": "string",
                "maxLength": 20000
              },
              "output": {
                "type": "string",
                "maxLength": 100000
              }
            },
            "required": [
              "severity",
              "input"
            ],
            "additionalProperties": false
          }
        }
      },
      "required": [
        "findings"
      ],
      "additionalProperties": false
    }
  }
}

Response

200 example

{
  "success": true
}

All status codes

200Generated guardrails + coverage + recommendations.
400(no description)
401(no description)
403Forbidden — the credential is valid but lacks the API-key scope, member role, or plan entitlement this operation requires.
429(no description)
500Internal Server Error — AUTO_GUARDRAIL_FAILED.

Code samples

cURL

curl -X POST \
  https://evalguard.ai/api/v1/security/auto-guardrails \
  -H "Authorization: Bearer $EVALGUARD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "findings": [ { "severity": "string", "input": "string", "type": "string", "category": "string", "attackCategory": "string", "title": "string", "description": "string", "output": "string" } ] }'

TypeScript

// The TypeScript SDK (@evalguard/sdk) exposes TYPED methods — runEval,
// getEval, runSecurityScan, checkFirewall, … — not a generic request().
// For an arbitrary endpoint, call it directly:

const res = await fetch("https://evalguard.ai/api/v1/security/auto-guardrails", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.EVALGUARD_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "findings": [
      {
        "severity": "string",
        "input": "string",
        "type": "string",
        "category": "string",
        "attackCategory": "string",
        "title": "string",
        "description": "string",
        "output": "string"
      }
    ]
  }),
});
console.log(res.status, await res.json());

Python

# The Python SDK (pip install evalguardai) exposes TYPED methods on
# EvalGuardClient — run_eval, get_eval, … — not a generic request().
# For an arbitrary endpoint, call it directly:

import os
import requests

headers = {"Authorization": f"Bearer {os.environ['EVALGUARD_API_KEY']}"}
headers["Content-Type"] = "application/json"

response = requests.request(
    "POST",
    "https://evalguard.ai/api/v1/security/auto-guardrails",
    headers=headers,
    json={
    "findings": [
        {
            "severity": "string",
            "input": "string",
            "type": "string",
            "category": "string",
            "attackCategory": "string",
            "title": "string",
            "description": "string",
            "output": "string"
        }
    ]
},
)
print(response.status_code, response.json())

Go

package main

import (
	"context"
	"fmt"
	"net/http"
	"os"
	"strings"
)

func main() {
	body := strings.NewReader(`{"findings":[{"severity":"string","input":"string","type":"string","category":"string","attackCategory":"string","title":"string","description":"string","output":"string"}]}`)
	req, _ := http.NewRequestWithContext(context.Background(), "POST", "https://evalguard.ai/api/v1/security/auto-guardrails", body)
	req.Header.Set("Authorization", "Bearer "+os.Getenv("EVALGUARD_API_KEY"))
	req.Header.Set("Content-Type", "application/json")
	resp, err := http.DefaultClient.Do(req)
	if err != nil { panic(err) }
	defer resp.Body.Close()
	fmt.Println(resp.Status)
}

Errors

400401403429500

Other Security endpoints